Tania S. Douglas

BACKGROUND: Mobile health (mHealth) has the potential to improve access to healthcare, especially in developing countries. The proliferation of mHealth has not been accompanied by a corresponding growth in design guidelines for mHealth applications. This paper proposes a framework for mHealth application design that combines the Information Systems Research (ISR) framework and design thinking. We demonstrate a use case for the proposed framework in the form of an app to read the result of the tuberculin skin test (TST), which is used to screen for latent tuberculosis infection. The framework was used in the re-design of the TST reading app but could also be used in earlier stages of mHealth app design. METHODS: The ISR framework and design thinking were merged based on how the modes of design thinking integrate with the cycles of the ISR framework. Using the combined framework, we re-designed an mHealth app for TST reading, intended to be used primarily in a developing context by healthcare workers. Using the proposed framework, the app was iterated upon and developed with the aid of personas, observations, prototyping and questionnaires. RESULT: The combined framework was applied through engagement with end-users, namely ten healthcare workers and ten graduate students. Through review of the literature and iterations of the app prototype, we identified various usability requirements and limitations. These included challenges related to image capture and a misunderstanding of instructions. These insights influenced the development and improvement of the app. CONCLUSION: The combined framework allowed for engagement with end-users and for low-cost, rapid development of the app while addressing contextual challenges and needs. The integration of design thinking modes with the ISR cycles was effective in achieving the objectives of each approach. The combined framework acknowledges the importance of engaging users when implementing mHealth technologies, especially in developing and under-resourced contexts. Findings from this study support the use of this framework as a guide in the design of user-centred mHealth interventions.

Near infrared spectroscopy (NIRS) is rapidly gaining popularity for functional brain imaging. It is well suited to studies of patients or children; however, in these populations particularly, motion artifacts can present a problem. Here, we propose the use of imaging channels with negligible distance between light source and detector to detect subject motion, without the need for an additional motion sensor. Datasets containing deliberate motion artifacts were obtained from three subjects. Motion artifacts could be detected in the signal from the co-located channels with a minimum sensitivity of 0.75 and specificity of 0.98. Five techniques for removing motion artifact from the functional signals were compared, namely two-input recursive least squares (RLS) adaptive filtering, wavelet-based filtering, independent component analysis (ICA), and two-channel and multiple-channel regression. In most datasets, the median change in SNR across all channels was the greatest using ICA or multiple-channel regression. RLS adaptive filtering produced the smallest increase in SNR. Where sharp spikes were present, wavelet filtering produced the largest SNR increase. ICA and multiple-channel regression are promising ways to reduce motion artifact in functional NIRS without requiring time-consuming manual techniques.

Screening for tuberculosis (TB) in low- and middle-income countries is centered on the microscope. We present methods for the automated identification of Mycobacterium tuberculosis in images of Ziehl-Neelsen (ZN) stained sputum smears obtained using a bright-field microscope. We segment candidate bacillus objects using a combination of two-class pixel classifiers. The algorithm produces results that agree well with manual segmentations, as judged by the Hausdorff distance and the modified Williams index. The extraction of geometric-transformation-invariant features and optimization of the feature set by feature subset selection and Fisher transformation follow. Finally, different two-class object classifiers are compared. The sensitivity and specificity of all tested classifiers is above 95% for the identification of bacillus objects represented by Fisher-transformed features. Our results may be used to reduce technician involvement in screening for TB, and would be particularly useful in laboratories in countries with a high burden of TB, where, typically, ZN rather than auramine staining of sputum smears is the method of choice.